A detection and severity estimation system for generic diseases of tomato greenhouse plants

•The shape of leaves alone has predictive power for disease recognition.•A general disease model can be trained to recognize previously unseen tomato leaf diseases.•Automatic disease severity estimation can achieve results comparable to those of human evaluation. The management of plant disease is a significant economic and environmental factor in the production of greenhouse tomato plants. Human expertise for assessing the presence and extent of disease is important in creating and implementing management plans, but it is difficult and expensive to acquire. In this paper, we present a new computer vision system to automatically recognize several diseases, detect previously unseen disease and to estimate per-leaf severity. Training and testing of models used several modified versions of the nine types of tomato disease of the PlantVillage tomato dataset and showed how different leaf properties impact disease detection.